© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 178367
    Prev
    Next
    INDEX
    Explanations

    record gets, mail or, contrast, predictions from

    np_acts-logits-general · gemini-2.5-flash-lite

    feels like ages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     ۵
    0.51
     azi
    0.50
     Jeu
    0.49
     Amir
    0.48
     ۴
    0.47
     млад
    0.47
     여섯
    0.47
     பெரிய
    0.46
     ۶
    0.46
     Preise
    0.46
    POSITIVE LOGITS
    FIL
    0.48
    GAL
    0.45
    LE
    0.45
    quota
    0.44
    LEGISLATIVE
    0.43
    diagnostic
    0.43
    awards
    0.42
    BOUR
    0.41
    filler
    0.41
    ILLA
    0.41
    Activations Density 0.000%

    No Known Activations